This is an automated email from the ASF dual-hosted git repository.
gurwls223 pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/master by this push:
new ce44afc413a [SPARK-43057][FOLLOWUP][CONNECT][PYTHON] Add & refine
errors
ce44afc413a is described below
commit ce44afc413abf494778ec6553c355937e51a44fb
Author: itholic <[email protected]>
AuthorDate: Wed May 3 19:42:27 2023 +0900
[SPARK-43057][FOLLOWUP][CONNECT][PYTHON] Add & refine errors
### What changes were proposed in this pull request?
This is follow-up for https://github.com/apache/spark/pull/40694 to redeem
some errors.
### Why are the changes needed?
To make errors clear
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
The existing CI should pass
Closes #41032 from itholic/connect_followup.
Authored-by: itholic <[email protected]>
Signed-off-by: Hyukjin Kwon <[email protected]>
---
python/pyspark/errors/error_classes.py | 5 +++++
python/pyspark/sql/connect/column.py | 10 ++++++----
2 files changed, 11 insertions(+), 4 deletions(-)
diff --git a/python/pyspark/errors/error_classes.py
b/python/pyspark/errors/error_classes.py
index 15a8bd5c3b3..2f559b6a538 100644
--- a/python/pyspark/errors/error_classes.py
+++ b/python/pyspark/errors/error_classes.py
@@ -34,6 +34,11 @@ ERROR_CLASSES_JSON = """
"Attribute `<attr_name>` in provided object `<obj_name>` is not
callable."
]
},
+ "ATTRIBUTE_NOT_SUPPORTED" : {
+ "message" : [
+ "Attribute `<attr_name>` is not supported."
+ ]
+ },
"BROADCAST_VARIABLE_NOT_LOADED": {
"message": [
"Broadcast variable `<variable>` not loaded."
diff --git a/python/pyspark/sql/connect/column.py
b/python/pyspark/sql/connect/column.py
index 7b60adb1629..2fdc3aabd4a 100644
--- a/python/pyspark/sql/connect/column.py
+++ b/python/pyspark/sql/connect/column.py
@@ -138,9 +138,9 @@ class Column:
# container operators
def __contains__(self, item: Any) -> None:
- raise ValueError(
- "Cannot apply 'in' operator against a column: please use
'contains' "
- "in a string column or 'array_contains' function for an array
column."
+ raise PySparkValueError(
+ error_class="CANNOT_APPLY_IN_FOR_COLUMN",
+ message_parameters={},
)
# bitwise operators
@@ -438,7 +438,9 @@ class Column:
error_class="JVM_ATTRIBUTE_NOT_SUPPORTED",
message_parameters={"attr_name": "_jc"}
)
if item.startswith("__"):
- raise AttributeError(item)
+ raise PySparkAttributeError(
+ error_class="ATTRIBUTE_NOT_SUPPORTED",
message_parameters={"attr_name": item}
+ )
return self[item]
def __getitem__(self, k: Any) -> "Column":
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
